Search

Based on hourly precipitation observations, the diurnal variation in precipitation and its seasonal evolution over the Yunnan–Guizhou Plateau (YGP) were analyzed. The results indicate that the seasonal variation in hourly rainfall in the western part of the YGP is unique. The rainfall reaches its hourly maximum during the late afternoon in spring (March–April) and during nighttime in summer (July–August), which contrasts with the pattern in most of eastern China. By further classifying the rainfall into short-duration (1–3 h) and long-duration (more than 6 h) events, the unique seasonal variations in the western YGP are found to mainly be comprised of short-duration rainfall. The long-duration rainfall shares similar diurnal peaks year-round for both the western and eastern parts of the YGP. The short-duration rainfall in the western part of the YGP shows a year-round afternoon peak, which is different from that of the eastern YGP, which peaks from midnight to early morning in spring and in the late afternoon in summer. The surface maximum daily temperature and low-level instabilities reach their annual maximum in spring over the western YGP and are also higher than in other parts of the YGP, together providing favorable conditions for convection to be triggered in spring afternoons over the western YGP. [ABSTRACT FROM AUTHOR]

To enhance the recommendation performance, session-based recommendations typically model based on graph neural networks (GNN). These models use the most recently clicked item as the user's short-term interest, as well as the query vector in the attention mechanism. Based on it, the attention score is calculated with the remaining items to obtain the user's long-term interest. However, the obtained representation of long-term interest is one-sided. Furthermore, unlike other recommendation technology, such as collaborative filtering that includes the user's entire history information, the session-based recommendation is more vulnerable to data sparsity. Existing models primarily make predictions based on observable user-item interactions and ignore items not interacted with by users. To address the aforementioned issues, we propose the denoising autoencoder integrated with self-supervised learning (SSL) in graph neural networks (DAS-GNN). In DAS-GNN, the query extraction module based on denoising autoencoder can mine multiple user interests and assist long-term interest to express user needs more comprehensively. We propose an effective way of dividing positive and negative samples in the SSL module and use adaptive thresholds to mine negative hard samples, thereby improving training efficiency and alleviating data sparsity. Extensive experiments demonstrate that the proposed DAS-GNN outperforms state-of-the-art models on four benchmarks. The source code is available at: https://github.com/daijiuqian/DAS-GNN. [ABSTRACT FROM AUTHOR]